Cargando…

Development of lung segmentation method in x-ray images of children based on TransResUNet

BACKGROUND: Chest x-ray (CXR) is widely applied for the detection and diagnosis of children's lung diseases. Lung field segmentation in digital CXR images is a key section of many computer-aided diagnosis systems. OBJECTIVE: In this study, we propose a method based on deep learning to improve t...

Descripción completa

Detalles Bibliográficos
Autores principales: Chen, Lingdong, Yu, Zhuo, Huang, Jian, Shu, Liqi, Kuosmanen, Pekka, Shen, Chen, Ma, Xiaohui, Li, Jing, Sun, Chensheng, Li, Zheming, Shu, Ting, Yu, Gang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10365102/
https://www.ncbi.nlm.nih.gov/pubmed/37492393
http://dx.doi.org/10.3389/fradi.2023.1190745
_version_ 1785076981822390272
author Chen, Lingdong
Yu, Zhuo
Huang, Jian
Shu, Liqi
Kuosmanen, Pekka
Shen, Chen
Ma, Xiaohui
Li, Jing
Sun, Chensheng
Li, Zheming
Shu, Ting
Yu, Gang
author_facet Chen, Lingdong
Yu, Zhuo
Huang, Jian
Shu, Liqi
Kuosmanen, Pekka
Shen, Chen
Ma, Xiaohui
Li, Jing
Sun, Chensheng
Li, Zheming
Shu, Ting
Yu, Gang
author_sort Chen, Lingdong
collection PubMed
description BACKGROUND: Chest x-ray (CXR) is widely applied for the detection and diagnosis of children's lung diseases. Lung field segmentation in digital CXR images is a key section of many computer-aided diagnosis systems. OBJECTIVE: In this study, we propose a method based on deep learning to improve the lung segmentation quality and accuracy of children's multi-center CXR images. METHODS: The novelty of the proposed method is the combination of merits of TransUNet and ResUNet. The former can provide a self-attention module improving the feature learning ability of the model, while the latter can avoid the problem of network degradation. RESULTS: Applied on the test set containing multi-center data, our model achieved a Dice score of 0.9822. CONCLUSIONS: This novel lung segmentation method proposed in this work based on TransResUNet is better than other existing medical image segmentation networks.
format Online
Article
Text
id pubmed-10365102
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-103651022023-07-25 Development of lung segmentation method in x-ray images of children based on TransResUNet Chen, Lingdong Yu, Zhuo Huang, Jian Shu, Liqi Kuosmanen, Pekka Shen, Chen Ma, Xiaohui Li, Jing Sun, Chensheng Li, Zheming Shu, Ting Yu, Gang Front Radiol Radiology BACKGROUND: Chest x-ray (CXR) is widely applied for the detection and diagnosis of children's lung diseases. Lung field segmentation in digital CXR images is a key section of many computer-aided diagnosis systems. OBJECTIVE: In this study, we propose a method based on deep learning to improve the lung segmentation quality and accuracy of children's multi-center CXR images. METHODS: The novelty of the proposed method is the combination of merits of TransUNet and ResUNet. The former can provide a self-attention module improving the feature learning ability of the model, while the latter can avoid the problem of network degradation. RESULTS: Applied on the test set containing multi-center data, our model achieved a Dice score of 0.9822. CONCLUSIONS: This novel lung segmentation method proposed in this work based on TransResUNet is better than other existing medical image segmentation networks. Frontiers Media S.A. 2023-04-27 /pmc/articles/PMC10365102/ /pubmed/37492393 http://dx.doi.org/10.3389/fradi.2023.1190745 Text en © 2023 Chen, Yu, Huang, Shu, Kuosmanen, Shen, Ma, Li, Sun, Li, Shu and Yu. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) (https://creativecommons.org/licenses/by/4.0/) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Radiology
Chen, Lingdong
Yu, Zhuo
Huang, Jian
Shu, Liqi
Kuosmanen, Pekka
Shen, Chen
Ma, Xiaohui
Li, Jing
Sun, Chensheng
Li, Zheming
Shu, Ting
Yu, Gang
Development of lung segmentation method in x-ray images of children based on TransResUNet
title Development of lung segmentation method in x-ray images of children based on TransResUNet
title_full Development of lung segmentation method in x-ray images of children based on TransResUNet
title_fullStr Development of lung segmentation method in x-ray images of children based on TransResUNet
title_full_unstemmed Development of lung segmentation method in x-ray images of children based on TransResUNet
title_short Development of lung segmentation method in x-ray images of children based on TransResUNet
title_sort development of lung segmentation method in x-ray images of children based on transresunet
topic Radiology
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10365102/
https://www.ncbi.nlm.nih.gov/pubmed/37492393
http://dx.doi.org/10.3389/fradi.2023.1190745
work_keys_str_mv AT chenlingdong developmentoflungsegmentationmethodinxrayimagesofchildrenbasedontransresunet
AT yuzhuo developmentoflungsegmentationmethodinxrayimagesofchildrenbasedontransresunet
AT huangjian developmentoflungsegmentationmethodinxrayimagesofchildrenbasedontransresunet
AT shuliqi developmentoflungsegmentationmethodinxrayimagesofchildrenbasedontransresunet
AT kuosmanenpekka developmentoflungsegmentationmethodinxrayimagesofchildrenbasedontransresunet
AT shenchen developmentoflungsegmentationmethodinxrayimagesofchildrenbasedontransresunet
AT maxiaohui developmentoflungsegmentationmethodinxrayimagesofchildrenbasedontransresunet
AT lijing developmentoflungsegmentationmethodinxrayimagesofchildrenbasedontransresunet
AT sunchensheng developmentoflungsegmentationmethodinxrayimagesofchildrenbasedontransresunet
AT lizheming developmentoflungsegmentationmethodinxrayimagesofchildrenbasedontransresunet
AT shuting developmentoflungsegmentationmethodinxrayimagesofchildrenbasedontransresunet
AT yugang developmentoflungsegmentationmethodinxrayimagesofchildrenbasedontransresunet